def load_model(self, model_path, classes_list, use_gpu=True):
if ("d0" in model_path):
self.system_dict["params"]["compound_coef"] = 0
self.system_dict["params"]["weights_file"] = model_path
elif ("d1" in model_path):
self.system_dict["params"]["compound_coef"] = 1
self.system_dict["params"]["weights_file"] = model_path
elif ("d2" in model_path):
self.system_dict["params"]["compound_coef"] = 2
self.system_dict["params"]["weights_file"] = model_path
elif ("d3" in model_path):
self.system_dict["params"]["compound_coef"] = 3
self.system_dict["params"]["weights_file"] = model_path
elif ("d4" in model_path):
self.system_dict["params"]["compound_coef"] = 4
self.system_dict["params"]["weights_file"] = model_path
elif ("d5" in model_path):
self.system_dict["params"]["compound_coef"] = 5
self.system_dict["params"]["weights_file"] = model_path
elif ("d6" in model_path):
self.system_dict["params"]["compound_coef"] = 6
self.system_dict["params"]["weights_file"] = model_path
elif ("d7" in model_path):
self.system_dict["params"]["compound_coef"] = 7
self.system_dict["params"]["weights_file"] = model_path
self.system_dict["params"]["obj_list"] = classes_list
self.system_dict["params"]["use_cuda"] = use_gpu
self.system_dict["local"]["color_list"] = standard_to_bgr(
STANDARD_COLORS)
# tf bilinear interpolation is different from any other's, just make do
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
self.system_dict["local"]["input_size"] = input_sizes[
self.system_dict["params"]["compound_coef"]] if self.system_dict[
"params"]["force_input_size"] is None else self.system_dict[
"params"]["force_input_size"]
self.system_dict["local"]["model"] = EfficientDetBackbone(
compound_coef=self.system_dict["params"]["compound_coef"],
num_classes=len(self.system_dict["params"]["obj_list"]),
ratios=self.system_dict["params"]["anchor_ratios"],
scales=self.system_dict["params"]["anchor_scales"])
self.system_dict["local"]["model"].load_state_dict(
torch.load(self.system_dict["params"]["weights_file"]))
self.system_dict["local"]["model"].requires_grad_(False)
self.system_dict["local"]["model"] = self.system_dict["local"][
"model"].eval()
if self.system_dict["params"]["use_cuda"]:
self.system_dict["local"]["model"] = self.system_dict["local"][
"model"].cuda()
if self.system_dict["params"]["use_float16"]:
self.system_dict["local"]["model"] = model.half()
def display(preds,
imgs,
compound_coef,
obj_list=None,
imshow=True,
imwrite=False,
debug=False):
if obj_list is None:
obj_list = ['person']
color_list = standard_to_bgr(STANDARD_COLORS)
for i in range(len(imgs)):
if len(preds[i]['rois']) == 0:
if debug:
cv2.imshow('img', imgs[i])
cv2.waitKey(0)
continue
imgs[i] = imgs[i].copy()
for j in range(len(preds[i]['rois'])):
x1, y1, x2, y2 = preds[i]['rois'][j].astype(np.int)
obj = obj_list[preds[i]['class_ids'][j]]
score = float(preds[i]['scores'][j])
plot_one_box(imgs[i], [x1, y1, x2, y2],
label=obj,
score=score,
color=color_list[get_index_label(obj, obj_list)])
if imshow:
cv2.imshow('img', imgs[i])
cv2.waitKey(0)
if imwrite:
os.system("mkdir -p ./assets/predictions")
cv2.imwrite(
f'./assets/predictions/img_inferred_d{compound_coef}_this_repo_{i}.jpg',
imgs[i])
if imwrite:
image_folder = './assets/predictions'
image_files = [
image_folder + '/' + img for img in os.listdir(image_folder)
if img.endswith(".jpg")
]
clip = moviepy.video.io.ImageSequenceClip.ImageSequenceClip(
image_files, fps=1)
clip.write_videofile('./assets/predictions_testset.mp4')
def __save_image(self, preds, imgs, imwrite=True):
color_list = standard_to_bgr(STANDARD_COLORS)
for i in range(len(imgs)):
if len(preds[i]['rois']) == 0:
continue
imgs[i] = imgs[i].copy()
for j in range(len(preds[i]['rois'])):
x1, y1, x2, y2 = preds[i]['rois'][j].astype(np.int)
obj = self.obj_list[preds[i]['class_ids'][j]]
score = float(preds[i]['scores'][j])
plot_one_box(imgs[i], [x1, y1, x2, y2],
label=obj,
score=score,
color=color_list[get_index_label(
obj, self.obj_list)])
if imwrite:
cv2.imwrite(
f'test/img_inferred_d{self.compound_coef}_this_repo_{i}.jpg',
imgs[i])
# replace this part with your project's anchor config
anchor_ratios = eval(params.anchor_ratios)
anchor_scales = eval(params.anchor_scales)
crop_size = params.crop_size
threshold = params.threshold
iou_threshold = params.iou_threshold
config = InferenceConfig()
use_cuda = True
use_float16 = False
cudnn.fastest = True
cudnn.benchmark = True
color_list = standard_to_bgr(STANDARD_COLORS)
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
model = EfficientDetBackbone(compound_coef=config.compound_coef,
num_classes=len(config.obj_list),
ratios=config.anchor_ratios,
scales=config.anchor_scales)
model.load_state_dict(torch.load(opt.weights))
model.requires_grad_(False)
model.eval()
if opt.command == 'report':
square_size = params.square_size
red_box = ((config.crop_size - square_size) / 2,
(config.crop_size - square_size) / 2,
(config.crop_size + square_size) / 2,
(config.crop_size + square_size) / 2)
def inference():
compound_coef = 0
force_input_size = None # set None to use default size
img_path = 'test/original_img.jpg'
# replace this part with your project's anchor config
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)]
threshold = 0.2
iou_threshold = 0.2
use_cuda = True
use_float16 = False
cudnn.fastest = True
cudnn.benchmark = True
obj_list = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', '', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
'cow', 'elephant', 'bear', 'zebra', 'giraffe', '', 'backpack', 'umbrella', '', '', 'handbag', 'tie',
'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove',
'skateboard', 'surfboard', 'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut',
'cake', 'chair', 'couch', 'potted plant', 'bed', '', 'dining table', '', '', 'toilet', '', 'tv',
'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
'toothbrush']
color_list = standard_to_bgr(STANDARD_COLORS)
# tf bilinear interpolation is different from any other's, just make do
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536, 1536]
input_size = input_sizes[2] if force_input_size is None else force_input_size
ori_imgs, framed_imgs, framed_metas = preprocess(img_path, max_size=input_size)
if use_cuda:
x = torch.stack([torch.from_numpy(fi).cuda() for fi in framed_imgs], 0)
else:
x = torch.stack([torch.from_numpy(fi) for fi in framed_imgs], 0)
x = x.to(torch.float32 if not use_float16 else torch.float16).permute(0, 3, 1, 2)
model = EfficientDet_semanticBackbone(compound_coef=1, num_classes=len(obj_list),
ratios=anchor_ratios, scales=anchor_scales)
model.load_state_dict(torch.load('model_weight/model_1_epoch_80.pth'))
if use_cuda:
model = model.cuda()
with torch.no_grad():
features, regression, classification, anchors, sem_out = model(x)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
out = postprocess(x,
anchors, regression, classification,
regressBoxes, clipBoxes,
threshold, iou_threshold)
out = invert_affine(framed_metas, out)
out = box(out, ori_imgs, color_list, obj_list, imshow=False, imwrite=False)
outputs = sem_out.data.cpu().numpy() # (shape: (batch_size, num_classes, img_h, img_w))
pred_label_imgs = np.argmax(outputs, axis=1) # (shape: (batch_size, img_h, img_w))
pred_label_imgs = pred_label_imgs.astype(np.uint8)
z = cv2.resize(pred_label_imgs[0], (ori_imgs[0].shape[1], ori_imgs[0].shape[0]))
from semantic_utils.utils import label_img_to_color
pred_label_img_color = label_img_to_color(z)
overlayed_img = 0.35*out + 0.65*pred_label_img_color
flag = cv2.imwrite('test/semantic_img_1.jpg', overlayed_img)
return flag
def test(opt):
compound_coef = 2
force_input_size = None # set None to use default size
img_id = opt.img_id
img_path = opt.img_path
img_path = img_path + str(img_id) + '.jpg'
# replace this part with your project's anchor config
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2**0, 2**(1.0 / 3.0), 2**(2.0 / 3.0)]
threshold = 0.2
iou_threshold = 0.2
use_cuda = True
use_float16 = False
cudnn.fastest = True
cudnn.benchmark = True
obj_list = ['02010001', '02010002']
color_list = standard_to_bgr(STANDARD_COLORS)
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536, 1536]
input_size = input_sizes[
compound_coef] if force_input_size is None else force_input_size
ori_imgs, framed_imgs, framed_metas = preprocess(img_path,
max_size=input_size)
if use_cuda:
x = torch.stack([torch.from_numpy(fi).cuda() for fi in framed_imgs], 0)
else:
x = torch.stack([torch.from_numpy(fi) for fi in framed_imgs], 0)
x = x.to(torch.float32 if not use_float16 else torch.float16).permute(
0, 3, 1, 2)
model = EfficientDetBackbone(compound_coef=compound_coef,
num_classes=len(obj_list),
ratios=anchor_ratios,
scales=anchor_scales)
model.load_state_dict(torch.load(opt.weights, map_location='cpu'))
model.requires_grad_(False)
model.eval()
if use_cuda:
model = model.cuda()
if use_float16:
model = model.half()
with torch.no_grad():
features, regression, classification, anchors = model(x)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
out = postprocess(x, anchors, regression, classification, regressBoxes,
clipBoxes, threshold, iou_threshold)
def display(preds, imgs, imshow=True, imwrite=False, img_id=1):
for i in range(len(imgs)):
if len(preds[i]['rois']) == 0:
continue
imgs[i] = imgs[i].copy()
imgs[i] = cv2.cvtColor(imgs[i], cv2.COLOR_BGR2RGB)
for j in range(len(preds[i]['rois'])):
x1, y1, x2, y2 = preds[i]['rois'][j].astype(np.int)
obj = obj_list[preds[i]['class_ids'][j]]
score = float(preds[i]['scores'][j])
plot_one_box(imgs[i], [x1, y1, x2, y2],
label=obj,
score=score,
color=color_list[get_index_label(obj, obj_list)])
if imshow:
cv2.imshow('img', imgs[i])
cv2.waitKey(0)
if imwrite:
str1 = 'test/' + str(img_id) + '.jpg'
cv2.imwrite(str1, imgs[i])
out = invert_affine(framed_metas, out)
display(out, ori_imgs, imshow=False, imwrite=True, img_id=img_id)
print('running speed test...')
with torch.no_grad():
print('test1: model inferring and postprocessing')
print('inferring image for 10 times...')
t1 = time.time()
for _ in range(10):
_, regression, classification, anchors = model(x)
out = postprocess(x, anchors, regression, classification,
regressBoxes, clipBoxes, threshold,
iou_threshold)
out = invert_affine(framed_metas, out)
tempList = []
for j in range(len(out[0]['class_ids'])):
tempout = {}
tempout['image_id'] = img_id
if out[0]['class_ids'][j] == 1:
tempout['category_id'] = 2
else:
tempout['category_id'] = 1
tempout['score'] = out[0]['scores'][j].astype(np.float64)
tempout['bbox'] = [
(out[0]['rois'][j][0]).astype(np.float64),
(out[0]['rois'][j][1]).astype(np.float64),
(out[0]['rois'][j][2]).astype(np.float64) -
(out[0]['rois'][j][0]).astype(np.float64),
(out[0]['rois'][j][3]).astype(np.float64) -
(out[0]['rois'][j][1]).astype(np.float64),
]
tempList.append(tempout)
t2 = time.time()
tact_time = (t2 - t1) / 10
print(f'{tact_time} seconds, {1 / tact_time} FPS, @batch_size 1')
with open("test/" + str(img_id) + ".json", "w") as f:
json.dump(tempList, f)
print("生成标注后的图片(" + str(img_id) + ".jpg)和json(" + str(img_id) +
".json)到test文件夹中...")